Supercharge your productivity with parallel AI teams and complete remote control. Version 1.37.0 transforms how you get work done by allowing multiple AI agents to tackle complex tasks simultaneously, while putting complete command of your workspace right inside your favorite messaging apps. • Parallel AI Teams: Time is your most valuable asset. Stop waiting for sequential responses. Our new Complex Task Planner allows specialized AI agents to work on multiple parts of your project at the exact same time. • Complete IM Command Center: Control your entire AI workspace from Slack or Discord without opening the app. Seamlessly switch models, swap chat flows, toggle knowledge bases, and manage tool access directly through simple chat commands, backed by robust connection stability and token-aware context truncation so chats never lag. • Advanced Tool Mastery: Customize exactly how your AI interacts with the world. Set default parameters for specific roles, enable global tool memory, and execute network requests with new cURL capabilities. We've also update web fetching to make online research cleaner and more accurate. • Expanded Cloud Horizons: Seamlessly tap into top-tier cloud models when you need maximum power. We now support AWS Bedrock, Z.ai (Zhipu GLM), Opencode Zen, Qwen Portal, and Kimi—with smarter auto-detection for vision models to make image analysis effortless. • Frictionless Experience: Focus on your work, not the setup. We've completely redesigned and streamlined the app settings, fixed tool-window freezes, and launched a comprehensive usage guide on our website to help you master every feature. Deploy AI teams that operate at the speed of thought, all orchestrated seamlessly from wherever you work. Update your On-Device AI experience today.

Turn every project into a connected AI workspace with seamless IM integration and active tools. This update brings real-time web search, advanced multi-flow chat management, and a high-speed modern speech engine directly to your device. • IM Connectivity (Mac): Connect your AI to Instant Messaging platforms (Discord, Slack, Telegram) to automate replies and manage conversations from your desktop. • Tool Calling & Web Search: Empower your agents with active tools. Integrated web search with a quick toggle brings real-time information into your chat. • Advanced Chat Flows: Manage multiple chat flows and keep different contexts organized. Now with flexible model switching for all users. • Enhanced User Experience: - Expanded Input Window: A larger workspace for defining characters and creative writing. - Optimized Interactions: Improved accessibility and control layout, particularly for spatial interactions on Vision Pro. - Cloud Provider Updates: A fresh look for cloud model settings. • Modern Speech-to-Text: Experience faster and more accurate voice transcription with the new built-in Modern Apple Speech-to-Text engine. • Responsive Feedback: Clear status indicators now keep you informed during intensive operations like high-quality speech generation, so you always know what's happening. Experience a more connected and capable AI with specialized tools, expanded connectivity, and a UI designed for creativity.

• GGUF Model Stability: Enhanced stability for GGUF models, ensuring smoother operation during offline inference • Smart Memory Management: Improved memory handling for both LLM inference and TTS generation, significantly reducing crashes on memory-constrained devices • Engine Upgrade: Updated MLX and llama.cpp engines to provided the latest performance and compatibility improvements • Adaptive TTS Engine: Automatically adjusts the Text-to-Speech engine based on available RAM during conversation mode for optimal stability • Better Keyboard Response: Optimized input handling for a snappier, more fluid typing experience during active conversations Experience a more stable and efficient local AI. Version 1.35.0 brings critical memory optimizations, engine updates, and adaptive TTS to ensure your assistant runs smoothly, even during complex tasks.

GGUF Vision Model Support • Run vision-capable GGUF models directly on your device for powerful image understanding without cloud dependency • Analyze photos, screenshots, documents, and diagrams using local vision models with complete privacy • Seamlessly switch between text-only and multimodal conversations Enhanced Camera & Vision Workflow • Updated camera mode allows capture image at free form for vision model analysis • Snap photos of real-world objects, whiteboards, or documents and get instant AI insights • More intuitive camera interface designed for quick visual queries Smarter Knowledge Libraries • Refactored embedding pipeline with session-based logic for more reliable document knowledge storage • Export and import knowledge packages to backup, share, or transfer your curated libraries between devices • Change embedding models directly from the main conversation screen for flexible document analysis Improved Audio Recording Experience • Better audio recording handling with more robust microphone management • Fixed potential microphone permission issues on iOS 26 for reliable voice capture • Smoother start/stop transitions and improved error recovery during recording sessions Whether you're analyzing images with local vision models, building portable knowledge libraries, or capturing voice notes with enhanced reliability, version 1.34.0 delivers more powerful and flexible on-device AI capabilities while keeping your data completely private.

Knowledge Libraries arrive in version 1.33.0, giving every project its own dedicated AI memory. Keep research clean, context focused, and documents exactly where your assistant expects them. Knowledge Libraries for serious projects: • Create a Library for each project or client and keep related notes, PDFs, and screenshots grouped together • Manage everything from one place, review document previews, then pull them into a conversation when you are ready • Library aware search focuses answers on the active Library for clearer, more trustable results • This release is the foundation, future updates will expand Knowledge Libraries with more powerful tools for organizing and sharing knowledge Conversation polish and engine reliability: • Scrolling in long conversations is smoother and more predictable, even with detailed exchanges • Keyboard reactions in the chat view are cleaner, reducing surprise jumps while typing and editing • Embedding model inference is more robust, with better indexing and fewer errors on large collections • Many small stability improvements make everyday work with documents and chat more dependable Whether you're managing separate research projects, client knowledge bases, or long-running personal libraries, version 1.33.0 gives you a powerful Knowledge Library system that keeps your AI organized, focused, and reliable.

Unlock powerful new ways to interact with your world in version 1.32.0. This update introduces groundbreaking vision capabilities for both local MLX models and cloud APIs, allowing you to analyze images and understand visual content like never before. We've also revolutionized web search with a new page-by-page reading mode for deeper, more accurate insights. Combined with a polished UI and a more robust MLX engine, your AI assistant is now more intelligent, perceptive, and reliable than ever. Multimodal Vision for Local & Cloud AI - MLX Vision Support: Analyze images directly on your device with select MLX models. Understand photos, diagrams, and real-world objects with complete privacy. - Take a picture of a plant and ask your local AI to identify it, all without an internet connection. - API Vision Integration: Leverage the power of advanced vision models from cloud providers. Get detailed descriptions, text extraction, and object recognition from services. - Upload a screenshot of a complex chart to get an instant summary and data analysis from a powerful cloud-based vision model. Deep Web Search with Page-by-Page Reading - Go beyond summaries with our new "Open for Web Search" feature. Your AI can now read web pages sequentially, gathering more accurate and detailed information for comprehensive research. - Ask your AI to research a complex topic, and it will read through multiple pages of a source article to give you a detailed and nuanced answer. Enhanced Performance & User Experience - Robust MLX Inference: We've hardened the MLX engine for greater stability, reducing errors and ensuring more reliable performance during long or complex tasks. - Polished UI: Enjoy a smoother, more intuitive experience with various UI updates designed to make your workflow more efficient and enjoyable. Whether you're identifying real world objects with a photo, extracting insights from complex charts, or conducting comprehensive research across the web, version 1.32.0 equips your AI assistant with the power of sight and deeper analytical intelligence. Experience the most perceptive and reliable On-Device AI yet.

Enhanced RAG Intelligence & Precision - Advanced embedding pipeline with improved semantic understanding and chunk scoring for more accurate document retrieval - Smart token budget calculations based on actual embedding model context sizes and chunk dimensions - Hybrid search combining vector similarity with text matching for comprehensive knowledge base queries - Research Workflows: Get more relevant citations and fewer off-topic results when analyzing multi-document knowledge bases - Academic Projects: Better context extraction from research papers with improved semantic grouping and relevance scoring Optimized Web Context Analysis - Cleaner webpage extraction with enhanced noise reduction and content structure preservation - Improved handling of dynamic content, JavaScript-rendered pages, and multi-step loading sequences - Better metadata capture including titles, authorship, and document structure for richer context - Web Research: Generate more focused summaries with reduced duplicate content and boilerplate text elimination - News Analysis: More accurate extraction of article content Performance & Stability Improvements - Smoother UI interactions with reduced memory usage and optimized state management across conversation screens - Resolved critical inference issues with GGUF model execution. - Enhanced GGUF model reliability with better error recovery and stable context handling - Improved embedding model loading with proper resource cleanup and memory management - Extended Sessions: More stable performance during long research projects with continuous document analysis and web browsing Transform your research and analysis workflows with smarter document understanding, cleaner web content extraction, and rock-solid performance. Whether conducting academic research with complex knowledge bases, analyzing web content for insights, or managing extended AI sessions, version 1.31.0 delivers the most intelligent and reliable On-Device AI experience yet.

Streamlined Model Import & Discovery - Import GGUF models directly from Hugging Face repositories with a simple URL or model identifier - Enhanced local model import with improved file handling, better error detection, and validation - Discover and download cutting-edge models from the community without leaving the app - Research Workflows: Quickly experiment with newly released models from Hugging Face for specialized tasks - Custom Solutions: Import organization-specific fine-tuned models directly from private or public repositories Enhanced Productivity Shortcuts - Expanded Mac hotkey system with customizable shortcuts for quick access to different app sections - iOS Quick Actions for launching directly into chat, voice recording, or document analysis from the home screen - Jump to specific features instantly without navigating through menus - Professional Workflows: Configure hotkeys for frequently used features like new conversation, voice recording, or model switching - Mobile Efficiency: Long-press the app icon on iOS to immediately start voice recording or open a specific tool Performance Optimizations & UI Refinements - Faster model loading times with optimized initialization sequences and improved memory allocation - Refined user interface with smoother animations, better visual hierarchy, and enhanced responsiveness - Reduced battery consumption during extended AI sessions Model Management Improvements - Better model validation during import with clear error messages and recovery suggestions - Enhanced compatibility detection to ensure imported models work optimally on your device - Improved model organization and categorization in the model picker - Quality Control: Automatic verification ensures imported models are compatible before adding to your library - Smart Recommendations: Get device-specific suggestions when importing models based on your hardware capabilities Experience seamless access to the world's largest AI model repository with direct Hugging Face integration, combined with lightning-fast shortcuts that put powerful AI tools at your fingertips. Version 1.30.0 makes it easier than ever to discover, import, and use cutting-edge AI models while maintaining the privacy and performance you expect from on-device processing.

Cloud Provider Integration - Connect to any compatible third party or self hosted API endpoint with your own key for access to powerful cloud models. - Seamlessly switch between on-device and cloud models within the same conversation for optimal performance and privacy balance - Business Use: Access latest Cloud Model for complex analysis while keeping sensitive data local on your device - Flexible Workflows: Use cloud models for heavy reasoning tasks and local models for quick responses or offline scenarios Enhanced Session Management - Remove individual attached documents from conversations with a simple tap on the close button - Clean up document references without affecting previous conversation responses - Research Projects: Dynamically manage your knowledge base by removing outdated PDFs or irrelevant images mid-session - Document Review: Add multiple files for comparison, then remove unnecessary ones to focus AI analysis on relevant materials Improved Inference Stability - Resolved memory management issues when switching between local and cloud models for smoother transitions - Enhanced error handling and recovery during model loading and inference processes - Multi-Model Workflows: Switch between local models and cloud APIs without performance degradation - Extended Sessions: More stable operation during long conversations with frequent model switching UI Refinements & Bug Fixes - Fixed display issues in model picker and settings interfaces for better user experience - Improved visual feedback and state indicators throughout the application - Streamlined Settings: Cleaner interface for managing both local and cloud model configurations - Better Discovery: Enhanced UI makes it easier to explore and configure cloud provider options Experience the perfect balance between privacy and power. Connect to cutting-edge cloud models when you need maximum capability, while keeping your sensitive data secure with local processing. Version 1.29.0 delivers the most flexible and stable AI experience yet, with seamless cloud integration and refined session management.

New section for Text-to-Speech Audio Generation - Generate speech audio from any text using Apple voices or Kokoro TTS model - Create voice-overs for presentations, convert articles to audio, or generate accessibility content Expanded AI Model Support - Added Embedding Gemma for enhanced semantic understanding and better document analysis - Improved context retention during long conversations and complex topic discussions Optimized Agent Flow Logic - Redesigned multi-agent collaboration for daily tasks like email drafting and project coordination - Agents automatically determine optimal workflow sequences for seamless collaboration Updated Inference Engine - Faster AI response times with improved memory efficiency, more stable iOS 26 Compatibility & Bug Fixes - Full iOS 26 optimization with improved system integration and Shortcuts support - Enhanced voice recognition accuracy and multi-agent coordination stability Transform your productivity with comprehensive voice capabilities, enhanced AI intelligence, and rock-solid performance. Whether creating audio content from text, conducting research with advanced embeddings, or managing complex multi-agent workflows, 1.28.0 version delivers the most versatile and stable On-Device AI experience yet.

Enhanced MLX Model Support - Improved compatibility and performance for MLX-based models, delivering faster inference and smoother operation on Apple Silicon devices - Expanded model library with support for GPT-OSS, Hunyuan, and other cutting-edge open-source models for even more flexible AI workflows Voice Experience & UI Improvements - Resolved voice playback issues for a more reliable and natural listening experience - Fixed rare cases where the model would continue "thinking" even when not in think mode, ensuring more predictable and responsive interactions - Updated voice picker interface for easier selection and a more intuitive user experience Performance & Stability - General bug fixes and optimizations for a smoother, more stable app experience Transform your productivity with rock-solid performance, expanded model capabilities, and refined voice interaction. Whether conducting extended research sessions, managing complex multi-model workflows, or relying on voice-first AI assistance, version 1.27.0 delivers the most stable and capable On-Device AI experience yet.

Introducing Kokoro TTS Model - Experience natural, human-like speech with our new advanced text-to-speech engine that delivers more expressive and emotionally nuanced voice responses - Customizable Speech Speed Control: Fine-tune voice playback speed from 0.5x to 2.0x to match your listening preferences and comprehension needs - Professional Presentations: Use slower speech speeds when presenting to audiences, or accelerate for quick personal review of lengthy content - Accessibility Support: Customize speech rates for different hearing preferences, learning disabilities, or language comprehension levels LaTeX Support in Markdown Mode - Render complex mathematical formulas, equations, and scientific notation directly within AI responses for academic and technical use cases - Enhanced markdown processing handles advanced formatting including tables, code blocks, and mathematical expressions seamlessly - Academic Research: Display complex mathematical proofs and scientific equations when working with STEM content or research papers - Educational Content: Render textbook-style mathematical notation when AI explains calculus, algebra, physics, or engineering concepts Improved Online Search & Noise-Resilient Voice - Enhanced error handling and connection stability for more consistent web-based research results with optimized search algorithms - Advanced audio processing filters background noise during voice interactions for clearer communication in challenging environments - Research Workflows: More reliable search results when conducting comprehensive research projects or fact-checking across multiple sources - Remote Work: Maintain clear voice conversations with AI even in noisy home offices, coffee shops, or shared workspaces Streamlined User Interface & Performance - Intuitive voice control indicators with real-time visual feedback during AI processing, generation, and speech playback phases - Enhanced subscription management with improved Pro feature discovery and reorganized settings for easier access - Professional Use: Better visual cues during client calls or presentations when using AI assistance without disrupting conversation flow - Extended Sessions: Improved memory management enables stable performance during long projects with continuous voice interaction Transform your productivity with natural voice communication, advanced content rendering, and reliable information retrieval. Whether conducting academic research with mathematical notation or working in challenging acoustic environments, version 1.26.0 delivers the most sophisticated and adaptable On-Device AI experience yet.

Revolutionary AI Team Collaboration - Create sophisticated AI teams with multi-agent chat flows where different specialized agents collaborate on complex tasks - Configure custom workflows with multiple AI roles working together sequentially - Built-in collaboration templates like "Plan Creator + Summarizer" for comprehensive problem-solving - Business Strategy: Deploy a "Market Analyst" agent to gather insights, then a "Strategic Planner" to create actionable plans, followed by a "Risk Assessor" to evaluate potential challenges - Creative Writing: Collaborate with an "Idea Generator" for brainstorming, a "Story Developer" for plot refinement, and an "Editor" for final polish Seamless macOS Integration - Keep On-Device AI readily available in your Mac's menu bar for instant access - Trigger AI conversations, voice recordings, or quick tasks with customizable hotkeys without leaving your current application - Get AI assistance while working in any Mac app with enhanced multitasking workflow - Professional Workflows: Use menu bar access and hotkeys to quickly transcribe meeting notes, translate content, or get instant AI assistance without interrupting your workflow - Cross-Application Integration: Seamlessly capture text from any Mac app, process it with AI, and return to your work without context switching Expanded AI Model Library - Access new cutting-edge models: Gemma-3n-E2B, Gemma-3n-E4B, Mistral Devstral Small, HuggingFace SmolLM3, Hunyuan A13B - Enhanced multilingual capabilities and specialized reasoning models for better global communication - Updated default built-in models for improved out-of-box experience Enhanced User Experience - Enjoy smoother text entry with improved prompt input interface featuring better formatting and real-time feedback - Experience faster model initialization with optimized MLX loading and clear progress indicators - Complex Problem Solving: Gain better visibility into AI reasoning processes to understand how agents approach multi-step challenges - Iterative Workflows: Refine prompts and experiment with different approaches more easily during creative or analytical tasks Performance & Reliability Improvements - Get your first AI model ready significantly faster with dramatically reduced startup time - Enjoy longer, more stable conversations with enhanced memory management - Urgent Consultations: Quick app startup lets you get AI help immediately during meetings or time-sensitive situations - Extended Research Sessions: Improved memory management enables hours-long research projects and complex multi-agent workflows without performance degradation Transform your productivity with AI teams that think together. Whether you're developing business strategies with multiple perspectives, conducting thorough research with specialized agents, or tackling creative projects that benefit from diverse AI viewpoints, version 1.25.0 delivers the most collaborative and accessible On-Device AI experience yet. Work smarter with AI that works as a team.

MLX Inference Engine Support - Revolutionary MLX inference support brings unprecedented performance optimization for Apple Silicon. - Faster processing speeds with reduced memory footprint - Native Apple hardware acceleration for smoother AI interactions Enhanced Voice Speech Experience - Pause & Resume Recording: Take control of your voice recordings with the new pause functionality - Seamless Conversation Mode: Experience natural, flowing speech conversations with automatic turn-taking - Hands-free interaction for truly conversational AI experiences - Perfect for extended voice sessions and natural dialogue flow Expanded Model Library - AI Models: Qwen3 MLX Models, Mistral Small 3.2 24B Instruct 2506, Menlo Jan Nano - Embedding Models: Qwen 3 Embedding: Performance & Stability Improvements - Optimized loading sequences for faster model initialization - Enhanced stability across all supported Apple devices - Improved battery efficiency during intensive AI operations - Refined user interface responsiveness Transform your productivity with MLX-powered speed, engage in natural voice conversations, and leverage our most comprehensive model selection yet. Whether you're conducting research, creating content, or having extended AI discussions, version 1.24.0 delivers the most responsive and capable On-Device AI experience to date.

* Custom Model Integration - Import any GGUF model directly into the app from your local device or via URL - Expand beyond built-in models with your own specialized AI configurations - Complete flexibility to use cutting-edge models as they become available * Added New AI Models Support - QwenLong L1 32B - DeepSeek R1 0528 Qwen3 8B - Qwen 3 Abliterated * Enhanced Performance & Stability - Significantly improved LLM inference processing with better resource management - Enhanced stability for longer AI conversations and complex tasks - Smart context size calculation based on your device's RAM and selected model - Real-time display of context usage percentage * Productivity Powerhouse - New temporary conversation mode for quick interactions without saving history - One-tap conversation cloning with the new clone button for easy experimentation - Effortless conversation regeneration to explore different AI responses - Enhanced iPad multitasking support - run On-Device AI alongside other apps in split or floating windows * Personalized Experience - Customizable main color themes in the "General & Appearance" section - Dynamic context size suggestions tailored to your device capabilities - Clear visibility of model context limits for better conversation planning * Improved Accuracy & Reliability - Enhanced precision for document analysis and web search results - More stable text-to-speech and speech-to-text integration - Better error handling and exception management throughout the app - Fix model loading issue at iPad Thank you to all who provided valuable suggestions and feedback. Your insights continue to drive meaningful improvements and new features

* Custom Model Integration - Import any GGUF model directly into the app from your local device or via URL - Expand beyond built-in models with your own specialized AI configurations - Complete flexibility to use cutting-edge models as they become available * Added New AI Models Support - QwenLong L1 32B - DeepSeek R1 0528 Qwen3 8B - Qwen 3 Abliterated * Enhanced Performance & Stability - Significantly improved LLM inference processing with better resource management - Enhanced stability for longer AI conversations and complex tasks - Smart context size calculation based on your device's RAM and selected model - Real-time display of context usage percentage * Productivity Powerhouse - New temporary conversation mode for quick interactions without saving history - One-tap conversation cloning with the new clone button for easy experimentation - Effortless conversation regeneration to explore different AI responses - Enhanced iPad multitasking support - run On-Device AI alongside other apps in split or floating windows * Personalized Experience - Customizable main color themes in the "General & Appearance" section - Dynamic context size suggestions tailored to your device capabilities - Clear visibility of model context limits for better conversation planning * Improved Accuracy & Reliability - Enhanced precision for document analysis and web search results - More stable text-to-speech and speech-to-text integration - Better error handling and exception management throughout the app Thank you to all who provided valuable suggestions and feedback. Your insights continue to drive meaningful improvements and new features

* Enhanced Model Performance - Optimized model loading with smoother transitions and better exception handling - Dramatically improved inference speed for long outputs - Refined resource management for more stable AI operations * Advanced Audio Management - Select and reuse previous audio recordings - Re-transcribe existing audio with different AI models - Run additional AI analysis on previously processed audio files - Perfect complement to the voice notes enhancements * UI Refinements - Added "Think" button in prompt input for triggering reasoning mode - Redesigned settings screen with dedicated role configuration section * New Model Support - Added full support for Phi4 reasoning capabilities - Expanded our growing model library - Bug Fixes & Stability Improvements - Various performance optimizations - Fixed minor UI inconsistencies - Improved error handling throughout the application

* Full Qwen3 Series Support: We've added complete integration for the Qwen3 series of AI models, bringing you more powerful language processing capabilities directly on your device. * Enhanced Voice Notes Experience: - Dynamic word highlighting follows along as audio plays - Jump to specific moments in recordings by tapping highlighted words - New export options: export transcriptions as .txt, .srt, or .md files - Perfect for creating subtitles, sharing notes, or archiving important conversations * Improved Model Controls: - Simplified toggle for reasoning mode in compatible AI models Easily switch reasoning on/off with a single tap - Get deeper analysis when needed or faster responses when speed matters * Performance & Stability - Faster Model Loading: Significant improvements to model initialization speeds get you working with AI more quickly - Flash Attention Now Off by Default: Changed default settings to prioritize system stability while maintaining excellent performance - More Reliable Online Search: Enhanced stability for web-based queries ensures consistent results - General Performance Optimizations: Various behind-the-scenes improvements for a smoother overall experience

- Introduce Role switch: You can now easily switch different system prompts with preferred model. - Voice Note Improvements: Access more conversation options after recording a voice memo. - Significant improvements in performance and robustness, including optimized model, resource loading, and much more. - Several UI Updated for smoother and more consistent dark mode experience. - Eliminated unnecessary download checks for the speech-to-text model. - Added Model compatibility for Deepcogito and DeepCoder models.

• With new audio import function you can translate audio files now! • Easily share and manage your audio files. • Enjoy continuous background recording while app in the background. • Updated user interface and refined layout. • Enhanced model grouping and filtering to help you find the right model easier. • Add dark mode icon. • Multiple bug fixes and model loading performance improvements.

• With new audio import function you can translate audio files now! • Easily share and manage your audio files. • Enjoy continuous background recording while app in the background. • Updated user interface and refined layout. • Enhanced model grouping and filtering to help you find the right model easier. • Add dark mode icon. • Multiple bug fixes and model loading performance improvements.

NEW AI Voice Note feature is available now! AI Voice Note supports: • Live audio translation • Save audio recordings securely • Automatic AI summaries after meetings Introduce pro membership plan: • Keep Everything You Love – All current features remain completely free plan, ensuring everyone enjoys great functionality. • Unlock Advanced Features – Exclusive access to upcoming premium functionalities for Pro members. New Model Support: • Added support for QwQ 32b and Gemma-3 Performance Improvements: • Optimized server-iPhone connectivity for smoother performance • Other UI and bug fix

• Added support for Phi-4 Mini, Granite 3.2, and Perplexity R1 models. • Moved search settings to the main search screen for easier access. • Improved performance with lazy loading for the embedding model method. • Fixed a potential crash when embedding documents. • Introduced a suggested model card for better recommendations.

- New search options and pre-planed mode. - Introduced LaTeX mode. - Added support for DeepScaleR-1.5B, Confucius-o1, UncensoredLM DeepSeek R1, Fuse o1 coder, and more. - Force start with thinking for reasoning model. - Bug fixes focusing on embedding logic. - Minor UI updates.

• Fixed an inference logic bug • Improved inference speed by fully loading the model into memory in auto mode • Added Deeplink support • iOS users can now share context directly with On-Device AI • Minor UI improvements